Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Introduction
- Comparing workflows and agents
- Overview of architecture and common application scenarios
Basics of the Claude API
- The Messages API, available models, and key parameters
- Creating system prompts and defining structured outputs
- Implementing streaming and handling errors
- Practical Exercise: Initial API integration
Implementing Tool Use
- Creating tools and defining their schemas
- Understanding the tool-use loop and recovering from errors
- Practical Exercise: Building an agent that interacts with internal company APIs
MCP and Agent Skills
- MCP server and client concepts
- Leveraging existing servers and developing a simple custom server
- Utilizing Agent Skills to encapsulate reusable knowledge
- Practical Exercise: Linking an agent to a data source
The Claude Agent SDK
- The agent loop, session management, and context control
- Managing permissions, hooks, and subagents
- Practical Exercise: Developing a research and reporting agent
Cost, Quality, and Safety
- Applying prompt caching and managing token budgets
- Setting up guardrails and requiring human approval for critical steps
- Conducting evaluations with a small test set
- Implementing logging and monitoring solutions
Moving from Prototype to Production
- Deployment strategies and secure management of secrets
- Long-term maintenance and version control
- Developing a roadmap for participants' specific use cases
Requirements
- Programming proficiency in Python or TypeScript
- Experience with making REST API calls and processing JSON data
- A foundational grasp of large language models
Target Audience
- Software developers and data engineers integrating AI features into products and internal systems
- Solution architects assessing different agent architectures
- Technical teams seeking to transition from prototyping to production-ready solutions
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
